MarkieMark1's picture
First try
11c833b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9055286645889282,
"min": 0.9055286645889282,
"max": 2.8560755252838135,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8685.8310546875,
"min": 8685.8310546875,
"max": 29217.65234375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.890697479248047,
"min": 0.24128876626491547,
"max": 12.913697242736816,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2513.68603515625,
"min": 46.810020446777344,
"max": 2634.394287109375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06755197669101072,
"min": 0.06551014441991392,
"max": 0.07625570770891785,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2702079067640429,
"min": 0.26204057767965566,
"max": 0.38127853854458926,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20891953215879552,
"min": 0.11630012558809683,
"max": 0.2984249147714353,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8356781286351821,
"min": 0.4652005023523873,
"max": 1.387410538453682,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.40909090909091,
"min": 2.977272727272727,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 131.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 2.977272727272727,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 131.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678871212",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1678871724"
},
"total": 512.3631464790001,
"count": 1,
"self": 0.7811855420000029,
"children": {
"run_training.setup": {
"total": 0.11725056900013442,
"count": 1,
"self": 0.11725056900013442
},
"TrainerController.start_learning": {
"total": 511.46471036799994,
"count": 1,
"self": 0.5904481770048733,
"children": {
"TrainerController._reset_env": {
"total": 12.801434256999983,
"count": 1,
"self": 12.801434256999983
},
"TrainerController.advance": {
"total": 497.8551891159955,
"count": 18214,
"self": 0.3299311550031234,
"children": {
"env_step": {
"total": 497.52525796099235,
"count": 18214,
"self": 351.715413515969,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.5113042269645,
"count": 18214,
"self": 2.2040802119704495,
"children": {
"TorchPolicy.evaluate": {
"total": 143.30722401499406,
"count": 18214,
"self": 143.30722401499406
}
}
},
"workers": {
"total": 0.2985402180588608,
"count": 18214,
"self": 0.0,
"children": {
"worker_root": {
"total": 509.68846827098514,
"count": 18214,
"is_parallel": true,
"self": 249.1320054999578,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023443569998562452,
"count": 1,
"is_parallel": true,
"self": 0.0006302870001491101,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017140699997071351,
"count": 10,
"is_parallel": true,
"self": 0.0017140699997071351
}
}
},
"UnityEnvironment.step": {
"total": 0.04228463100025692,
"count": 1,
"is_parallel": true,
"self": 0.00046392500053116237,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047498100002485444,
"count": 1,
"is_parallel": true,
"self": 0.00047498100002485444
},
"communicator.exchange": {
"total": 0.039950376999968285,
"count": 1,
"is_parallel": true,
"self": 0.039950376999968285
},
"steps_from_proto": {
"total": 0.0013953479997326212,
"count": 1,
"is_parallel": true,
"self": 0.0003203720002602495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010749759994723718,
"count": 10,
"is_parallel": true,
"self": 0.0010749759994723718
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.5564627710273,
"count": 18213,
"is_parallel": true,
"self": 10.270548062961097,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.940954382036125,
"count": 18213,
"is_parallel": true,
"self": 5.940954382036125
},
"communicator.exchange": {
"total": 208.79524677095606,
"count": 18213,
"is_parallel": true,
"self": 208.79524677095606
},
"steps_from_proto": {
"total": 35.54971355507405,
"count": 18213,
"is_parallel": true,
"self": 7.179728293182052,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.369985261891998,
"count": 182130,
"is_parallel": true,
"self": 28.369985261891998
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001606759997230256,
"count": 1,
"self": 0.0001606759997230256,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 493.5155814469649,
"count": 454019,
"is_parallel": true,
"self": 11.742060219069117,
"children": {
"process_trajectory": {
"total": 277.2949454398977,
"count": 454019,
"is_parallel": true,
"self": 275.476422934898,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8185225049996916,
"count": 4,
"is_parallel": true,
"self": 1.8185225049996916
}
}
},
"_update_policy": {
"total": 204.47857578799812,
"count": 90,
"is_parallel": true,
"self": 76.84885143799102,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.62972435000711,
"count": 4587,
"is_parallel": true,
"self": 127.62972435000711
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2174781419998908,
"count": 1,
"self": 0.0014048839998395124,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21607325800005128,
"count": 1,
"self": 0.21607325800005128
}
}
}
}
}
}
}